Top postsTop post
The April 2026 Iliad Intensive cohort, at LISA Iliad, an umbrella organization for applied math for AI alignment, is running several additional programs through the end of the year! Applications to all of them are now open, here. Applicants will be selected on the basis of estimated mathematical strength. August...
We are releasing the course materials of the Iliad Intensive, a new month-long and full-time AI Alignment course that runs in-person every second month. The course targets people with strong backgrounds in mathematics, physics, or theoretical computer science, and the materials reflect that: they include mathematical exercises with solutions, self-contained...
Almost two months ago, Iliad announced the Iliad Intensive and Iliad Fellowship. Fellowships are a well-understood unit, but what is an intensive? This post explains this in more detail! For more details on the content, see the Iliad Intensive Course Materials post. Comparison. The Iliad Intensive has similarities to ARENA,...
We are pleased to announce ILIAD 2026— official title: ILIADIII:AENEID, a 5-day conference bringing together researchers to build scientific foundations for AI alignment. This is the 3rd iteration of ILIAD, which was first held in the summer of 2024. ***Apply to attend by July 1!*** * When: Aug 3-7, 2026...
Iliad is proud to announce that applications are now open for the Iliad Intensive and the Iliad Fellowship! These programs, taken together, are our evolution of the PIBBSS × Iliad Research Residency pilot. The Iliad Intensive will cover taught coursework, serving as a widely comprehensive introduction to the field of...
Iliad is now opening up applications to attend Agent Foundations 2026 at CMU! Agent Foundations 2026 will be a 5-day conference (of ~35 attendees) on fundamental, mathematical research into agency. It will take place March 2–6, 2026 at Carnegie Mellon University in Pittsburgh, Pennsylvania, and will be the third conference...
Repo: https://github.com/DavidUdell/sparse_circuit_discovery TL;DR: A SPAR project from a while back. A replication of an unsupervised circuit discovery algorithm in GPT-2-small, with a negative result. Thanks to Justis Mills for draft feedback and to Neuronpedia for interpretability data. Introduction I (David) first heard about sparse autoencoders at a Bay Area party....